What Should Data Teach? Moving Bottlenecks Across Circuit, Store, and Use
cs.LG
Submitted: 2026-09-26
Updated: 2026-09-26
Terminology
Sources
- Physics of Language Models: Part 3.2, Knowledge Manipulation
- Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
- Extending Context Window of Large Language Models via Positional Interpolation
- Symbolic Mechanistic Data Attribution: Tracing Training Influence to Learned Behavioral Policies
- Mechanistic Circuit Identification for Controllable Data Generation
- Induction Signatures Are Not Enough: A Matched-Compute Study of Load-Bearing Structure in In-Context Learning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks